Saltar al cuntegna

Stable Audio 3 Medium Audio to Audio

Integrar

ID dal model stable-audio-3/medium/audio-to-audio
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/stable-audio-3/medium/audio-to-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Questa dumonda: $0,042 42 credits API Lantschar sin questa pagina

Obtegna ina clav API
Stability AI Audio 1–380 s #music#style-transfer#remix

Stable Audio 3 Medium distillà che remixescha in clip d'origin en ina nova variaziun dad in prompt

Stability AI · Audio

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori

Instrucziuns da text che descrivan la transfurmaziun d'applitgar a l'audio da funtauna.

•obligatori audio_url
Trametta in datoteca u

Audio input per la transfurmaziun.

standard 30

Lunghezza da l'audio en secunda, cun in maximum per il model mesaun da 380 secunda (circa 6 minutas 20 secunda).

Avanzà negative_prompt · output_format · bitrate · num_inference_steps · guidance_scale · init_noise_level · seed · enable_prompt_expansion · enable_safety_checker
standard

Text che specifitgescha qualitads nungiavischadas en l'output.

output_format standard mp3

Format dal container utilisà per l'audio resultant.

standard 192k

Bitrate da l'audio output, ignorà cun wav u flac perquai ch'els èn senza perdita. Per formats cumprimids sco mp3, aac u opus, furni ina valur en la furma '192k' u '320k'.

standard 8

Dumber d'iteraziuns da sampling, cun standard 8, perquai che checkpoints distillads e post-scolads cuntanschan gia ina buna qualitad là; iteraziuns supplementaras portan pauc avantatg.

standard 1

Furma da classifier-free guidance mo per checkpoints da basa; checkpoints distillads na vegnan betg influenzads. En checkpoints adattads rinforza l'augment l'aderenza al prompt.

standard 0.9

Nivel da ramur da l'audio da funtauna: 0.1 mantegna ina gronda sumeglientscha cun l'input, 0.5 è intermediar e 1.0 remplazza cumplettamain la funtauna cun ramur per ina generaziun pura.

Sem dal generator aleatoric per resultats repetibels; sch'el manca, vegn tschernì in sem casual.

POST /run/stable-audio-3/medium/audio-to-audio?wait=20 calculaziun → $0,042
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/stable-audio-3/medium/audio-to-audio?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart Stable Audio 3 Medium Audio to Audio

Transfurma `audio_url` tenor in `prompt` e producescha audio cun ina `duration` dad 1 fin 380 secundas (standard 30). `init_noise_level` da 0 fin 1 determinescha quant stretgamain il resultat suonda la funtauna: ina valur bassa mantegna el datiers, 1.0 munta generaziun cumpletta. Il standard è 8 pass, cun plirs formats d'output disponibels.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
negative_promptopziunal
Tipstring
Standard
Text che specifitgescha qualitads nungiavischadas en l'output.
durationopziunal
Tipnumber
Standard30
1 – 380
Lunghezza da l'audio en secunda, cun in maximum per il model mesaun da 380 secunda (circa 6 minutas 20 secunda).
num_inference_stepsopziunal
Tipinteger
Standard8
1 – 100
Dumber d'iteraziuns da sampling, cun standard 8, perquai che checkpoints distillads e post-scolads cuntanschan gia ina buna qualitad là; iteraziuns supplementaras portan pauc avantatg.
guidance_scaleopziunal
Tipnumber
Standard1
0 – 25
Furma da classifier-free guidance mo per checkpoints da basa; checkpoints distillads na vegnan betg influenzads. En checkpoints adattads rinforza l'augment l'aderenza al prompt.
seedopziunal
Tipinteger | null
Sem dal generator aleatoric per resultats repetibels; sch'el manca, vegn tschernì in sem casual.
enable_prompt_expansionopziunal
Tipboolean
Standardfalse
Expansiun dal prompt cun in LLM sche activada, che agiunta detagls e meglierescha la qualitad dal resultat.
enable_safety_checkeropziunal
Tipboolean
Standardtrue
Controlla da segirezza per cuntegns NSFW.
output_formatopziunal
Tipenum
Standardmp3
mp3wavflacoggopusm4aaac
Format dal container utilisà per l'audio resultant.
bitrateopziunal
Tipstring
Standard192k
Bitrate da l'audio output, ignorà cun wav u flac perquai ch'els èn senza perdita. Per formats cumprimids sco mp3, aac u opus, furni ina valur en la furma '192k' u '320k'.
promptobligatori
Tipstring
Instrucziuns da text che descrivan la transfurmaziun d'applitgar a l'audio da funtauna.
audio_urlobligatori audio
Tipurl · audio
Audio input per la transfurmaziun.
init_noise_levelopziunal
Tipnumber
Standard0.9
0 – 1
Nivel da ramur da l'audio da funtauna: 0.1 mantegna ina gronda sumeglientscha cun l'input, 0.5 è intermediar e 1.0 remplazza cumplettamain la funtauna cun ramur per ina generaziun pura.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "stable-audio-3/medium/audio-to-audio",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 42,
    "usd": "0.042",
    "charged": 42,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
audio
object {url, content_type, file_name, file_size}Clip audio producì tras generaziun.
seed
integerSeed che controllava la casualitad durant la generaziun.
prompt
stringPrompt utilisà per generar l'output.

Dapli models: Audio

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/stable-audio-3/medium/audio-to-audio.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt